I find the watermarking dynamic to be really interesting in the legal space, as more large model providers provide increasingly powerful legal capabilities, and adoption (presumably) also increases. Attorneys aren’t the same as developers as their work can be traced back to them, and there are personal bar licenses and reputations at stake. I wonder if knowing the likelihood that AI generated something helps or hurts in that respect.
I also see a lot of watermark removal services popping up as a result.
> By using the legal search index, Astra for Law can search U.S. case law, statutes, regulations, court rules, and administrative decisions across a corpus of more than 230 million URLs, with sources added daily. Our work with Free Law Project, the nonprofit behind CourtListener, brings its case-law collection covering more than 99.9% of published U.S. precedential case law (opens in a new window) into this research experience.
CourtListener already has an MCP interface and Grok is quite good at pulling from it. In my experience, Grok 4.6 is quite good at analyzing legal cases and human-written documents. Better than Opus 5. I'm not sure if it's better than Fable 5.1 on that task, b/c I'm not willing to spend my precious Fable tokens on case law searches lol.
Man I can't count the number of shell wrappers I've written or reached out to over my career. Looking forward to having an official Swift SubProcess helper.
I'm building SMS alerts for Kalshi market movements, upset alerts, big trades, specific teams and more. Starting a private beta (if interested, send a message via X @OddsLineSMS).
Whole-file rewrites for small changes. When editing text files, the model is more likely to rewrite the entire file than make a targeted edit. The result is usually the same, but the rewrite costs more output tokens and time.
So we are to catch that somehow? And then add their recommendation (below) to our prompts?
If Claude Fable 5.1 rewrites whole files for small changes, append the following instruction to the system prompt or the first user message. Claude Fable 5.1 is more likely than Claude Fable 5 to rewrite an entire text file rather than make a targeted edit. The resulting file is usually the same, but unless the file is short or most of it is changing, a rewrite costs more output tokens and time. The instruction brings Claude Fable 5.1 back in line with Claude Fable 5 for small and medium changes.
> The number of tokens used to edit files is best minimized, all else being equal. Therefore, when it will not affect the end result, try to surgically edit a file rather than rewrite the entire thing.
That's actually kind of wild. I wonder if part of this was done to catch out people using 3rd party harnesses, users might notice them costing more than Claude Code.
They imply that Claude Design can handle the design work for anything serious. I understand it's still marked as 'beta' but in my team's experience it is a long way away from being ready for this kind of flow.
> Our evaluation found Thomson’s citation quality generally competitive with leading frontier models, even when tested on Canadian employment-law questions without a Canada-specific setting.
That’s it? It was generally competitive with leading frontier models? Neat, but why would someone pay for frontier models and also a generally competitive additional product?
I also see a lot of watermark removal services popping up as a result.
reply